{"list":"other","total":92,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2201.05989","title":"Instant Neural Graphics Primitives with a Multiresolution Hash Encoding","created":"2022-01-16","cited_by_count":3723},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"2103.13415","title":"Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields","created":"2021-03-24","cited_by_count":1964},{"id":"2312.14132","title":"DUSt3R: Geometric 3D Vision Made Easy","created":"2023-12-21","cited_by_count":1567},{"id":"2011.13961","title":"D-NeRF: Neural Radiance Fields for Dynamic Scenes","created":"2020-11-27","cited_by_count":1465},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"2203.09517","title":"TensoRF: Tensorial Radiance Fields","created":"2022-03-17","cited_by_count":1280},{"id":"2011.12948","title":"Nerfies: Deformable Neural Radiance Fields","created":"2020-11-25","cited_by_count":1198},{"id":"2310.08528","title":"4D Gaussian Splatting for Real-Time Dynamic Scene Rendering","created":"2023-10-12","cited_by_count":1157},{"id":"1704.00675","title":"The 2017 DAVIS Challenge on Video Object Segmentation","created":"2017-04-03","cited_by_count":957},{"id":"2309.13101","title":"Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction","created":"2023-09-22","cited_by_count":759},{"id":"2011.13084","title":"Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes","created":"2020-11-26","cited_by_count":751},{"id":"2301.10241","title":"K-Planes: Explicit Radiance Fields in Space, Time, and Appearance","created":"2023-01-24","cited_by_count":746},{"id":"2308.09713","title":"Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis","created":"2023-08-18","cited_by_count":737},{"id":"1607.08128","title":"Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image","created":"2016-07-27","cited_by_count":695},{"id":"2108.10869","title":"DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras","created":"2021-08-24","cited_by_count":687},{"id":"2302.12288","title":"ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth","created":"2023-02-23","cited_by_count":657},{"id":"2301.09632","title":"HexPlane: A Fast Representation for Dynamic Scenes","created":"2023-01-23","cited_by_count":587},{"id":"2307.07635","title":"CoTracker: It is Better to Track Together","created":"2023-07-14","cited_by_count":522},{"id":"2201.04127","title":"HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Video","created":"2022-01-11","cited_by_count":483},{"id":"2310.10642","title":"Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting","created":"2023-10-16","cited_by_count":476},{"id":"2012.12247","title":"Non-Rigid Neural Radiance Fields: Reconstruction and Novel View Synthesis of a Dynamic Scene From Monocular Video","created":"2020-12-22","cited_by_count":471},{"id":"2207.07115","title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","created":"2022-07-14","cited_by_count":439},{"id":"2105.06468","title":"Dynamic View Synthesis from Dynamic Monocular Video","created":"2021-05-13","cited_by_count":420},{"id":"2011.12950","title":"Space-time Neural Irradiance Fields for Free-Viewpoint Video","created":"2020-11-25","cited_by_count":414},{"id":"2404.15506","title":"Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation","created":"2024-03-22","cited_by_count":395},{"id":"2403.18913","title":"UniDepth: Universal Monocular Metric Depth Estimation","created":"2024-03-27","cited_by_count":382},{"id":"2312.14937","title":"SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes","created":"2023-12-04","cited_by_count":347},{"id":"2205.15285","title":"Fast Dynamic Radiance Fields with Time-Aware Neural Voxels","created":"2022-05-30","cited_by_count":346},{"id":"2312.16812","title":"Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesis","created":"2023-12-28","cited_by_count":344},{"id":"2012.09790","title":"Neural Radiance Flow for 4D View Synthesis and Video Processing","created":"2020-12-17","cited_by_count":270},{"id":"2404.10772","title":"Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenes","created":"2024-04-16","cited_by_count":232},{"id":"2204.04153","title":"Particle Video Revisited: Tracking Through Occlusions Using Point Trajectories","created":"2022-04-08","cited_by_count":217},{"id":"2106.13228","title":"HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fields","created":"2021-06-24","cited_by_count":214},{"id":"2312.03431","title":"Gaussian-Flow: 4D Reconstruction with Dynamic 3D Gaussian Particle","created":"2023-12-06","cited_by_count":211},{"id":"2210.13445","title":"Monocular Dynamic View Synthesis: A Reality Check","created":"2022-10-24","cited_by_count":200},{"id":"2112.12761","title":"BANMo: Building Animatable 3D Neural Models from Many Casual Videos","created":"2021-12-23","cited_by_count":197},{"id":"2309.03903","title":"Tracking Anything with Decoupled Video Segmentation","created":"2023-09-07","cited_by_count":197},{"id":"2312.09228","title":"3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting","created":"2023-12-14","cited_by_count":195},{"id":"2301.02239","title":"Robust Dynamic Radiance Fields","created":"2023-01-05","cited_by_count":194},{"id":"2312.02134","title":"GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians","created":"2023-12-04","cited_by_count":191},{"id":"2208.04726","title":"Deep Patch Visual Odometry","created":"2022-08-08","cited_by_count":190},{"id":"2402.03307","title":"4D-Rotor Gaussian Splatting: Towards Efficient Novel View Synthesis for Dynamic Scenes","created":"2024-02-05","cited_by_count":189},{"id":"2012.05901","title":"Robust Consistent Video Depth Estimation","created":"2020-12-10","cited_by_count":188},{"id":"2404.04319","title":"SpatialTracker: Tracking Any 2D Pixels in 3D Space","created":"2024-04-05","cited_by_count":181},{"id":"2301.02238","title":"HyperReel: High-Fidelity 6-DoF Video with Ray-Conditioned Sampling","created":"2023-01-05","cited_by_count":174},{"id":"2403.05087","title":"SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splatting","created":"2024-03-08","cited_by_count":172},{"id":"2312.02973","title":"GauHuman: Articulated Gaussian Splatting from Monocular Human Videos","created":"2023-12-05","cited_by_count":168},{"id":"2004.01294","title":"Novel View Synthesis of Dynamic Scenes with Globally Coherent Depths from a Monocular Camera","created":"2020-04-02","cited_by_count":166},{"id":"1804.03786","title":"Nonlinear 3D Face Morphable Model","created":"2018-04-11","cited_by_count":157},{"id":"2311.17910","title":"HUGS: Human Gaussian Splats","created":"2023-11-29","cited_by_count":154},{"id":"2210.15947","title":"NeRFPlayer: A Streamable Dynamic Scene Representation with Decomposed Neural Radiance Fields","created":"2022-10-28","cited_by_count":152},{"id":"2205.15838","title":"D$^2$NeRF: Self-Supervised Decoupling of Dynamic and Static Objects from a Monocular Video","created":"2022-05-31","cited_by_count":137},{"id":"2206.06481","title":"RigNeRF: Fully Controllable Neural 3D Portraits","created":"2022-06-13","cited_by_count":126},{"id":"2312.00112","title":"DynMF: Neural Motion Factorization for Real-time Dynamic View Synthesis with 3D Gaussian Splatting","created":"2023-11-30","cited_by_count":124},{"id":"2311.16099","title":"GART: Gaussian Articulated Template Models","created":"2023-11-27","cited_by_count":121},{"id":"2402.00847","title":"BootsTAP: Bootstrapped Training for Tracking-Any-Point","created":"2024-02-01","cited_by_count":120},{"id":"2105.02976","title":"LASR: Learning Articulated Shape Reconstruction from a Monocular Video","created":"2021-05-06","cited_by_count":116},{"id":"2312.11458","title":"GauFRe: Gaussian Deformation Fields for Real-time Dynamic Novel View Synthesis","created":"2023-12-18","cited_by_count":95},{"id":"2207.09137","title":"ParticleSfM: Exploiting Dense Point Trajectories for Localizing Moving Cameras in the Wild","created":"2022-07-19","cited_by_count":92},{"id":"2312.04558","title":"MonoGaussianAvatar: Monocular Gaussian Point-based Head Avatar","created":"2023-12-07","cited_by_count":89},{"id":"2105.05994","title":"Neural Trajectory Fields for Dynamic Novel View Synthesis","created":"2021-05-12","cited_by_count":86},{"id":"2005.13532","title":"4D Visualization of Dynamic Events from Unconstrained Multi-View Videos","created":"2020-05-27","cited_by_count":66},{"id":"2403.14548","title":"DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video","created":"2024-03-21","cited_by_count":64},{"id":"2212.13056","title":"MonoNeRF: Learning a Generalizable Dynamic Radiance Field from Monocular Videos","created":"2022-12-26","cited_by_count":63},{"id":"2405.02280","title":"DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos","created":"2024-05-03","cited_by_count":63},{"id":"2312.01196","title":"Neural Parametric Gaussians for Monocular Non-Rigid Object Reconstruction","created":"2023-12-02","cited_by_count":61},{"id":"2401.01887","title":"LEAP-VO: Long-term Effective Any Point Tracking for Visual Odometry","created":"2024-01-03","cited_by_count":56},{"id":"2310.08585","title":"Im4D: High-Fidelity and Real-Time Novel View Synthesis for Dynamic Scenes","created":"2023-10-12","cited_by_count":55},{"id":"2404.07991","title":"GoMAvatar: Efficient Animatable Human Modeling from Monocular Video Using Gaussians-on-Mesh","created":"2024-04-11","cited_by_count":51},{"id":"2006.13240","title":"Neural Non-Rigid Tracking","created":"2020-06-23","cited_by_count":49},{"id":"2207.10606","title":"Approximate Differentiable Rendering with Algebraic Surfaces","created":"2022-07-21","cited_by_count":44},{"id":"2310.18999","title":"DynPoint: Dynamic Neural Point For View Synthesis","created":"2023-10-29","cited_by_count":37},{"id":"2312.15258","title":"Human101: Training 100+FPS Human Gaussians in 100s from 1 View","created":"2023-12-23","cited_by_count":32},{"id":"1904.13073","title":"SurfelWarp: Efficient Non-Volumetric Single View Dynamic Reconstruction","created":"2019-04-30","cited_by_count":31},{"id":"2010.00450","title":"X-Fields: Implicit Neural View-, Light- and Time-Image Interpolation","created":"2020-10-01","cited_by_count":31},{"id":"2404.01053","title":"HAHA: Highly Articulated Gaussian Human Avatars with Textured Mesh Prior","created":"2024-04-01","cited_by_count":31},{"id":"2308.14737","title":"Flexible Techniques for Differentiable Rendering with 3D Gaussians","created":"2023-08-28","cited_by_count":28},{"id":"2310.08587","title":"Pseudo-Generalized Dynamic View Synthesis from a Video","created":"2023-10-12","cited_by_count":27},{"id":"2402.16607","title":"GVA: Reconstructing Vivid 3D Gaussian Avatars from Monocular Videos","created":"2024-02-26","cited_by_count":22},{"id":"2401.04861","title":"CTNeRF: Cross-Time Transformer for Dynamic Neural Radiance Field from Monocular Video","created":"2024-01-10","cited_by_count":18},{"id":"2401.05583","title":"Diffusion Priors for Dynamic View Synthesis from Monocular Videos","created":"2024-01-10","cited_by_count":18},{"id":"2304.01716","title":"Decoupling Dynamic Monocular Videos for Dynamic View Synthesis","created":"2023-04-04","cited_by_count":17},{"id":"2402.03723","title":"Rig3DGS: Creating Controllable Portraits from Casual Monocular Videos","created":"2024-02-06","cited_by_count":16}],"next_cursor":null}